Skip to main content
Fine-tuning adapts a base model to your data: your tone, formats, tasks, or domain. Omnia runs the training and lets you deploy the result to a dedicated endpoint, callable through the same API as any other model. The management API lives at https://gateway.omnia-voice.com/v1 and uses your workspace API key.

​
The workflow

1

Prepare a dataset

Format your training data as JSONL, or use a managed dataset with column mapping. See Datasets & formats.
2

Create a fine-tuning job

Choose a base model and training data, pick a method and hyperparameters, and start the job. See Creating a job.
3

Track progress

Jobs move through queued → running → succeeded (or failed / cancelled). Events and checkpoints are available while the job runs.
4

Deploy the model

A completed job produces a model artifact. Deploy it to a dedicated endpoint and call it by its routing key. See Deploying a fine-tuned model.

​
Methods

Omnia supports two training methods, selected with the method field on a job:

Supervised

Standard supervised fine-tuning, either LoRA (efficient adapter training) or full fine-tuning, with the usual hyperparameters: epochs, learning rate, batch size, context length, and LoRA rank/alpha.

Spec-draft

Train a speculative-draft model, configured via its own specDraftHyperparameters.

​
Billing

Fine-tuning is billed per trained token, charged once when the job completes. Failed or cancelled jobs aren’t billed.
The exact trained_tokens isn’t known until a run finishes, so the create-time gate uses an estimated-token budget: a workspace can’t launch a training run it can’t pay for. The final charge is settled from the actual trained-token count on completion.

​
Datasets

You can upload training files directly (JSONL), bring data from S3-compatible Object Storage, or use Omnia’s managed datasets with column-mapping into the training format. Data is validated before a job starts, and real validation errors are surfaced with the exact reason so you can fix them before spending on a job. See Datasets & formats.

​
Using a trained model

A completed job produces a model artifact. Fine-tuned models are served on dedicated capacity (not the shared per-token fleet): create a dedicated endpoint with customWeightsId (the artifact id) or fineTuningJobId, then call it via model = dedicated/<routing-key>. See Deploying a fine-tuned model.

Prepare data

Formats, uploads, and validation.

Start a job

Create your first fine-tuning job.